<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Cli - Tag - EONYX Blog</title><link>https://eonyx.tech/blog/tags/cli/</link><description>Cli - Tag - EONYX Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>eonyx.tech@proton.me (EONYX)</managingEditor><webMaster>eonyx.tech@proton.me (EONYX)</webMaster><copyright>This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</copyright><lastBuildDate>Fri, 03 Jul 2026 00:00:00 +0300</lastBuildDate><atom:link href="https://eonyx.tech/blog/tags/cli/" rel="self" type="application/rss+xml"/><item><title>Installing EONYX: build, run, and configure</title><link>https://eonyx.tech/blog/eonyx-setup/</link><pubDate>Fri, 03 Jul 2026 00:00:00 +0300</pubDate><author><name>EONYX</name></author><guid>https://eonyx.tech/blog/eonyx-setup/</guid><description><![CDATA[<div class="featured-image">
                <img src="/blog/eonyx-setup/cover.svg" referrerpolicy="no-referrer">
            </div><p><strong>EONYX</strong> is a terminal AI agent for working with code, written in <a href="https://go.dev" target="_blank" rel="noopener noreferrer">Go</a>. It connects directly to any OpenAI-compatible API (<a href="https://openai.com" target="_blank" rel="noopener noreferrer">OpenAI</a>, <a href="https://openrouter.ai" target="_blank" rel="noopener noreferrer">OpenRouter</a>, <a href="https://www.deepseek.com" target="_blank" rel="noopener noreferrer">DeepSeek</a>, <a href="https://www.moonshot.ai" target="_blank" rel="noopener noreferrer">Moonshot</a>, local <a href="https://ollama.com" target="_blank" rel="noopener noreferrer">Ollama</a> / <a href="https://github.com/ggml-org/llama.cpp" target="_blank" rel="noopener noreferrer">llama.cpp</a> / <a href="https://lmstudio.ai" target="_blank" rel="noopener noreferrer">LM Studio</a>) — no external services, no telemetry, no OAuth. One process, one binary, everything local. Here: installation, the first run, and the full configuration.</p>]]></description></item><item><title>EONYX vs Claude Code: an honest comparison</title><link>https://eonyx.tech/blog/eonyx-vs-claude-code/</link><pubDate>Mon, 15 Jun 2026 00:00:00 +0300</pubDate><author><name>EONYX</name></author><guid>https://eonyx.tech/blog/eonyx-vs-claude-code/</guid><description><![CDATA[<div class="featured-image">
                <img src="/blog/eonyx-vs-claude-code/cover.svg" referrerpolicy="no-referrer">
            </div><p><strong>EONYX</strong> and <strong><a href="https://www.anthropic.com/claude-code" target="_blank" rel="noopener noreferrer">Claude Code</a></strong> are both terminal AI agents for working with code, and their workflow is similar: <a href="https://modelcontextprotocol.io" target="_blank" rel="noopener noreferrer">MCP</a>, skills, hooks, subagents, plan mode, sessions. The difference is in the architecture and the freedom. Claude Code is tied to the cloud and to <a href="https://www.anthropic.com" target="_blank" rel="noopener noreferrer">Anthropic</a> models; EONYX is not. Here is what that gives you in practice.</p>]]></description></item><item><title>EONYX Headless Mode: Running the Agent Without the TUI</title><link>https://eonyx.tech/blog/eonyx-headless/</link><pubDate>Tue, 19 May 2026 00:00:00 +0300</pubDate><author><name>EONYX</name></author><guid>https://eonyx.tech/blog/eonyx-headless/</guid><description><![CDATA[<div class="featured-image">
                <img src="/blog/eonyx-headless/cover.svg" referrerpolicy="no-referrer">
            </div><p>Besides the interactive TUI, EONYX can run <strong>headless</strong> — perform a task and exit. That is what you need for scripts, pipes and CI: predictable output, JSON events and meaningful exit codes.</p>]]></description></item></channel></rss>